Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0685. Min Range: -5.0685
Max Act: 5.0685. Min Act: -0.1700
Data Index: 5484827 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0685. Min Range: -5.0685
Max Act: 5.0060. Min Act: -0.1700
Data Index: 3856700 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.8498. Min Act: -0.1700
Data Index: 3137530 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.8498. Min Act: -0.1700
Data Index: 6953829 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3950011 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7873. Min Act: -0.1700
Data Index: 3939333 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7873. Min Act: -0.1700
Data Index: 2121620 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7873. Min Act: -0.1700
Data Index: 796391 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7560. Min Act: -0.1700
Data Index: 3719519 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7560. Min Act: -0.1700
Data Index: 4179955 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1567472 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7248. Min Act: -0.1700
Data Index: 6414369 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.7560. Min Act: -0.1700
Data Index: 3862520 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6935. Min Act: -0.1700
Data Index: 8039234 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6935. Min Act: -0.1700
Data Index: 2333118 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6935. Min Act: -0.1700
Data Index: 4213962 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6935. Min Act: -0.1700
Data Index: 5062145 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6935. Min Act: -0.1700
Data Index: 6950858 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6623. Min Act: -0.1700
Data Index: 8248880 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0685. Min Range: -5.0685
Max Act: 4.6623. Min Act: -0.1700
Data Index: 2580068 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19